Split and merge algorithm for deep learning and its application for additional classes

Hongsub An

doi:10.1016/j.patrec.2015.07.024

Return

Split and merge algorithm for deep learning and its application for additional classes

2015-11-01

PRE

DOI：10.1016/j.patrec.2015.07.024

Original

Original request for help

Save

Abstract

En 中文

In this paper, we propose a novel split training and merge algorithm for deep learning. The proposed algorithm improves recognition accuracy and suggests a new approach for retraining. The algorithm is motivated by the genetic algorithm (GA) and is composed of two procedures. The first procedure initializes two individual networks using deep belief networks (DBNs), and the second procedure merges the two networks using the GA. Biases and weights of the network that is trained using DBNs are represented as a matrix between each layer, and each row of this matrix is used as a chromosome in the merge procedure. To evaluate the performance, we conduct two set of experiments. The first set is to recognize accuracy of the proposed algorithm, and the second set is for a new retraining approach. The results show that the proposed algorithm has a lower average error rate (6.34 +/- 4.57%) than the DBNs, and it can add classes at a lower average error rate (9.06 +/- 6.17% and 10.17 +/- 4.51%) without pre-training using the restrict Boltzmann machines (RBMs) for existing classes data. (C) 2015 Elsevier B.V. All rights reserved.

Keywords:

Deep neural networks

Genetic algorithm

Deep belief networks

Feature extractor

AI Summary

Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.